{"adoption": {"forks": 160, "observed_at": "2026-08-28T04:06:40.487483+00:00", "stars": 2353}, "canonical_url": "https://ross.abutalabs.com/products/perception_models", "card": {"archived": false, "artifact_type": "library", "description": "State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!", "domain": ["computer-vision", "deep-learning", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "deep-learning", "computer-vision", "image-processing", "video-processing", "audio-processing", "llm-inference", "transformers"], "health_score": 66, "homepage": null, "language": "Jupyter Notebook", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["facebookresearch/perception_models"], "name": "facebookresearch/perception_models", "platform": ["python", "cross-platform"], "pushed_at": "2026-04-13T21:42:56+00:00", "repo": "facebookresearch/perception_models", "stars": 2353, "tags": ["clip", "perception-encoder", "perception-language-model", "multimodal", "embeddings", "video-understanding", "audiovisual", "pytorch", "model-checkpoints", "facebook-research", "video", "audio", "natural-language-processing", "gpu"], "topics": [], "urls": [], "use_cases": ["encode images and videos into embeddings for retrieval", "run zero-shot image and video classification with CLIP-style models", "build video question answering with a multimodal language model", "evaluate multimodal models on PLM-VideoBench", "extract audio-visual embeddings for cross-modal search", "fine-tune vision-language models on custom video data"], "what_it_is": "Meta's Perception Models repository hosting state-of-the-art image, video, and audio encoders (Perception Encoder, PE) and a multimodal language model (Perception Language Model, PLM). It provides pretrained checkpoints, evaluation benchmarks, and integrations with Hugging Face transformers and timm.", "when_to_avoid": ["you need lightweight CPU-only inference without GPU resources", "you need a production application rather than research models and checkpoints", "you need text-only language modeling without vision or audio"], "when_to_choose": ["you need state-of-the-art visual or audiovisual embeddings for retrieval or classification", "you want an open multimodal LLM for video understanding tasks", "you want models already integrated into Hugging Face transformers or timm"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/perception_models", "repo": "facebookresearch/perception_models", "role": "main", "score": 54}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:40.487483+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:36:29.473148+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c7791a3800449b4e0d6bf6cef78a41fc76d8aeca848312c32efbc654e970704e", "fetched_at": "2026-08-28T04:06:40.487483+00:00", "kind": "readme", "missing": false, "url": "https://github.com/facebookresearch/perception_models"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 77, "longevity": 36, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 504, "days_push": 142, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 54, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}